Destava

Reinforcement Learning Engineer (Autonomous Driving)

42dot is hiring for Reinforcement Learning Engineer (Autonomous Driving) in Pangyo (Software Dream Center), South Korea. Mid level. First seen October 14, 2026; open as of November 10, 2026. Jobs taken straight from company career pages — no aggregator in between.

Save to applyRead more and apply on 42dot's site

With Destava: How well do you fit? · Tailor my résumé · Write a cover letter

Company
42dot
Where
Pangyo (Software Dream Center), South Korea
Level
Mid
First seen
October 14, 2026
Listed via
Ashby

What the posting says

RESPONSIBILITIES - VLA policy와 simulator의 observation/action interface를 설계하고 GRPO, PPO 등 policy optimization 기법으로 closed-loop RL post-training을 개발합니다. - Vector 또는 occupancy 기반 driving simulator에서 ego와 traffic agent가 학습 중인 policy 및 과거 checkpoint로 상호작용하는 self-play training 구조를 개발합니다. - 학습된 policy의 candidate action과 trajectory를 여러 가능한 future scenario에서 rollout하고, expected return과 safety constraint에 기반한 action selection을 simulation 환경 개발 담당자와 공동 개발합니다. - Closed-loop benchmark로 policy의 안전성과 일반화를 검증하고 reward hacking 및 simulator bias를 분석합니다. QUALIFICATIONS - Machine Learning, Reinforcement Learning…

Read more and apply on 42dot's site

This page includes information from the O*NET 31.0 Database by the U.S. Department of Labor, Employment and Training Administration (USDOL/ETA). Used under the CC BY 4.0 license. O*NET® is a trademark of USDOL/ETA.